Merge remote-tracking branch 'origin/deploy/dev' into deploy/dev

api/app.py

@@ -1,12 +1,8 @@
-from libs import version_utils
-
-# preparation before creating app
-version_utils.check_supported_python_version()
+import os
+import sys
 
 
 def is_db_command():
-    import sys
-
     if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
         return True
     return False
@@ -18,10 +14,25 @@ def is_db_command():
 
     app = create_migrations_app()
 else:
-    from app_factory import create_app
-    from libs import threadings_utils
+    # It seems that JetBrains Python debugger does not work well with gevent,
+    # so we need to disable gevent in debug mode.
+    # If you are using debugpy and set GEVENT_SUPPORT=True, you can debug with gevent.
+    if (flask_debug := os.environ.get("FLASK_DEBUG", "0")) and flask_debug.lower() in {"false", "0", "no"}:
+        from gevent import monkey  # type: ignore
+
+        # gevent
+        monkey.patch_all()
+
+        from grpc.experimental import gevent as grpc_gevent  # type: ignore
 
-    threadings_utils.apply_gevent_threading_patch()
+        # grpc gevent
+        grpc_gevent.init_gevent()
+
+        import psycogreen.gevent  # type: ignore
+
+        psycogreen.gevent.patch_psycopg()
+
+    from app_factory import create_app
 
     app = create_app()
     celery = app.extensions["celery"]

api/controllers/console/app/completion.py

@@ -20,7 +20,6 @@
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
-    AppInvokeQuotaExceededError,
     ModelCurrentlyNotSupportError,
     ProviderTokenNotInitError,
     QuotaExceededError,
@@ -76,7 +75,7 @@ def post(self, app_model):
             raise ProviderModelCurrentlyNotSupportError()
         except InvokeError as e:
             raise CompletionRequestError(e.description)
-        except (ValueError, AppInvokeQuotaExceededError) as e:
+        except ValueError as e:
             raise e
         except Exception as e:
             logging.exception("internal server error.")
@@ -141,7 +140,7 @@ def post(self, app_model):
             raise InvokeRateLimitHttpError(ex.description)
         except InvokeError as e:
             raise CompletionRequestError(e.description)
-        except (ValueError, AppInvokeQuotaExceededError) as e:
+        except ValueError as e:
             raise e
         except Exception as e:
             logging.exception("internal server error.")

api/controllers/console/app/statistic.py

@@ -273,8 +273,7 @@ def get(self, app_model):
             messages m
             ON c.id = m.conversation_id
         WHERE
-            c.override_model_configs IS NULL
-            AND c.app_id = :app_id"""
+            c.app_id = :app_id"""
         arg_dict = {"tz": account.timezone, "app_id": app_model.id}
 
         timezone = pytz.timezone(account.timezone)

api/controllers/console/explore/completion.py

@@ -18,7 +18,11 @@
 from controllers.console.explore.wraps import InstalledAppResource
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
+from core.errors.error import (
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
 from core.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
 from libs import helper

api/controllers/console/explore/workflow.py

@@ -13,7 +13,11 @@
 from controllers.console.explore.wraps import InstalledAppResource
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
+from core.errors.error import (
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
 from core.model_runtime.errors.invoke import InvokeError
 from libs import helper
 from libs.login import current_user

api/controllers/service_api/app/completion.py

@@ -18,7 +18,6 @@
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
-    AppInvokeQuotaExceededError,
     ModelCurrentlyNotSupportError,
     ProviderTokenNotInitError,
     QuotaExceededError,
@@ -74,7 +73,7 @@ def post(self, app_model: App, end_user: EndUser):
             raise ProviderModelCurrentlyNotSupportError()
         except InvokeError as e:
             raise CompletionRequestError(e.description)
-        except (ValueError, AppInvokeQuotaExceededError) as e:
+        except ValueError as e:
             raise e
         except Exception as e:
             logging.exception("internal server error.")
@@ -133,7 +132,7 @@ def post(self, app_model: App, end_user: EndUser):
             raise ProviderModelCurrentlyNotSupportError()
         except InvokeError as e:
             raise CompletionRequestError(e.description)
-        except (ValueError, AppInvokeQuotaExceededError) as e:
+        except ValueError as e:
             raise e
         except Exception as e:
             logging.exception("internal server error.")

api/controllers/service_api/app/workflow.py

@@ -16,7 +16,6 @@
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
-    AppInvokeQuotaExceededError,
     ModelCurrentlyNotSupportError,
     ProviderTokenNotInitError,
     QuotaExceededError,
@@ -94,7 +93,7 @@ def post(self, app_model: App, end_user: EndUser):
             raise ProviderModelCurrentlyNotSupportError()
         except InvokeError as e:
             raise CompletionRequestError(e.description)
-        except (ValueError, AppInvokeQuotaExceededError) as e:
+        except ValueError as e:
             raise e
         except Exception as e:
             logging.exception("internal server error.")

api/controllers/service_api/dataset/document.py

@@ -190,7 +190,10 @@ def post(self, tenant_id, dataset_id):
             user=current_user,
             source="datasets",
         )
-        data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
+        data_source = {
+            "type": "upload_file",
+            "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
+        }
         args["data_source"] = data_source
         # validate args
         knowledge_config = KnowledgeConfig(**args)
@@ -254,7 +257,10 @@ def post(self, tenant_id, dataset_id, document_id):
                 raise FileTooLargeError(file_too_large_error.description)
             except services.errors.file.UnsupportedFileTypeError:
                 raise UnsupportedFileTypeError()
-            data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
+            data_source = {
+                "type": "upload_file",
+                "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
+            }
             args["data_source"] = data_source
         # validate args
         args["original_document_id"] = str(document_id)

api/controllers/web/completion.py

@@ -19,7 +19,11 @@
 from controllers.web.wraps import WebApiResource
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
+from core.errors.error import (
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
 from core.model_runtime.errors.invoke import InvokeError
 from libs import helper
 from libs.helper import uuid_value

api/controllers/web/workflow.py

@@ -14,7 +14,11 @@
 from controllers.web.wraps import WebApiResource
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
+from core.errors.error import (
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
 from core.model_runtime.errors.invoke import InvokeError
 from libs import helper
 from models.model import App, AppMode, EndUser

api/core/app/apps/advanced_chat/app_generator.py

@@ -21,7 +21,7 @@
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
 from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom
 from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
-from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
+from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.ops.ops_trace_manager import TraceQueueManager
 from core.prompt.utils.get_thread_messages_length import get_thread_messages_length
 from extensions.ext_database import db
@@ -336,7 +336,7 @@ def _generate_worker(
             except ValidationError as e:
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
-            except (ValueError, InvokeError) as e:
+            except ValueError as e:
                 if dify_config.DEBUG:
                     logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)

api/core/app/apps/agent_chat/app_generator.py

@@ -18,7 +18,7 @@
 from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
 from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity, InvokeFrom
-from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
+from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
@@ -245,7 +245,7 @@ def _generate_worker(
             except ValidationError as e:
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
-            except (ValueError, InvokeError) as e:
+            except ValueError as e:
                 if dify_config.DEBUG:
                     logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)

api/core/app/apps/chat/app_generator.py

@@ -18,7 +18,7 @@
 from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
 from core.app.entities.app_invoke_entities import ChatAppGenerateEntity, InvokeFrom
-from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
+from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
@@ -237,7 +237,7 @@ def _generate_worker(
             except ValidationError as e:
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
-            except (ValueError, InvokeError) as e:
+            except ValueError as e:
                 if dify_config.DEBUG:
                     logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)

api/core/app/apps/completion/app_generator.py

@@ -17,7 +17,7 @@
 from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
 from core.app.entities.app_invoke_entities import CompletionAppGenerateEntity, InvokeFrom
-from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
+from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
@@ -214,7 +214,7 @@ def _generate_worker(
             except ValidationError as e:
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
-            except (ValueError, InvokeError) as e:
+            except ValueError as e:
                 if dify_config.DEBUG:
                     logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)

api/core/app/apps/workflow/app_generator.py

@@ -20,7 +20,7 @@
 from core.app.apps.workflow.generate_task_pipeline import WorkflowAppGenerateTaskPipeline
 from core.app.entities.app_invoke_entities import InvokeFrom, WorkflowAppGenerateEntity
 from core.app.entities.task_entities import WorkflowAppBlockingResponse, WorkflowAppStreamResponse
-from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
+from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
@@ -221,6 +221,7 @@ def single_iteration_generate(
             single_iteration_run=WorkflowAppGenerateEntity.SingleIterationRunEntity(
                 node_id=node_id, inputs=args["inputs"]
             ),
+            workflow_run_id=str(uuid.uuid4()),
         )
         contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
 
@@ -270,7 +271,7 @@ def _generate_worker(
             except ValidationError as e:
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
-            except (ValueError, InvokeError) as e:
+            except ValueError as e:
                 if dify_config.DEBUG:
                     logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)

api/core/app/entities/app_invoke_entities.py

@@ -195,7 +195,7 @@ class WorkflowAppGenerateEntity(AppGenerateEntity):
 
     # app config
     app_config: WorkflowUIBasedAppConfig
-    workflow_run_id: Optional[str] = None
+    workflow_run_id: str
 
     class SingleIterationRunEntity(BaseModel):
         """

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -102,7 +102,8 @@ def _handle_workflow_run_start(
         inputs = dict(WorkflowEntry.handle_special_values(inputs) or {})
 
         # init workflow run
-        workflow_run_id = str(self._workflow_system_variables.get(SystemVariableKey.WORKFLOW_RUN_ID, uuid4()))
+        # TODO: This workflow_run_id should always not be None, maybe we can use a more elegant way to handle this
+        workflow_run_id = str(self._workflow_system_variables.get(SystemVariableKey.WORKFLOW_RUN_ID) or uuid4())
 
         workflow_run = WorkflowRun()
         workflow_run.id = workflow_run_id
@@ -274,7 +275,7 @@ def _handle_node_execution_start(
         self, *, session: Session, workflow_run: WorkflowRun, event: QueueNodeStartedEvent
     ) -> WorkflowNodeExecution:
         workflow_node_execution = WorkflowNodeExecution()
-        workflow_node_execution.id = event.node_execution_id
+        workflow_node_execution.id = str(uuid4())
         workflow_node_execution.tenant_id = workflow_run.tenant_id
         workflow_node_execution.app_id = workflow_run.app_id
         workflow_node_execution.workflow_id = workflow_run.workflow_id
@@ -391,7 +392,7 @@ def _handle_workflow_node_execution_retried(
         execution_metadata = json.dumps(merged_metadata)
 
         workflow_node_execution = WorkflowNodeExecution()
-        workflow_node_execution.id = event.node_execution_id
+        workflow_node_execution.id = str(uuid4())
         workflow_node_execution.tenant_id = workflow_run.tenant_id
         workflow_node_execution.app_id = workflow_run.app_id
         workflow_node_execution.workflow_id = workflow_run.workflow_id
@@ -824,7 +825,7 @@ def _get_workflow_run(self, *, session: Session, workflow_run_id: str) -> Workfl
         return workflow_run
 
     def _get_workflow_node_execution(self, session: Session, node_execution_id: str) -> WorkflowNodeExecution:
-        stmt = select(WorkflowNodeExecution).where(WorkflowNodeExecution.id == node_execution_id)
+        stmt = select(WorkflowNodeExecution).where(WorkflowNodeExecution.node_execution_id == node_execution_id)
         workflow_node_execution = session.scalar(stmt)
         if not workflow_node_execution:
             raise WorkflowNodeExecutionNotFoundError(node_execution_id)

api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenzier.py

@@ -1,11 +1,13 @@
+from concurrent.futures import ProcessPoolExecutor
 from os.path import abspath, dirname, join
 from threading import Lock
-from typing import Any
+from typing import Any, cast
 
 from transformers import GPT2Tokenizer as TransformerGPT2Tokenizer  # type: ignore
 
 _tokenizer: Any = None
 _lock = Lock()
+_executor = ProcessPoolExecutor(max_workers=1)
 
 
 class GPT2Tokenizer:
@@ -20,7 +22,9 @@ def _get_num_tokens_by_gpt2(text: str) -> int:
 
     @staticmethod
     def get_num_tokens(text: str) -> int:
-        return GPT2Tokenizer._get_num_tokens_by_gpt2(text)
+        future = _executor.submit(GPT2Tokenizer._get_num_tokens_by_gpt2, text)
+        result = future.result()
+        return cast(int, result)
 
     @staticmethod
     def get_encoder() -> Any:

api/core/model_runtime/model_providers/groq/llm/gemma-7b-it.yaml

@@ -18,6 +18,18 @@ parameter_rules:
     default: 512
     min: 1
     max: 8192
+  - name: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
 pricing:
   input: '0.05'
   output: '0.1'